This is the official portfolio of Arman Zhalgasbayev, here you can learn more about him and his
professional experience! Thank you for visiting the webpage, with love mr. Arman 梦想
Research and Development Engineer 🛠️
Supply chain optimization system using LGBM time series forecasting models for predictive analysis of sales and stock levels, enabling proactive warehouse management.
Developed a platform for analyzing and visualizing data on mining incidents.
Developed optimized algorithm combining Dijkstra for minimum pathfinding and time-greedy approach for efficient goods distribution with minimal empty travel time.
Excelled in the "Machine Learning" track of Yandex's prestigious programming and data analysis competition.
Represented Kazakhstan in the international Tech4Good competition, developing innovative solutions for global challenges.
Beyim Insight - AI system for generating detailed SMART reports on student's test/mock exams including feedback, recommendations, visualizations and predictions for various exams (UNT, NUET, IELTS, TOEFL, MESC, SAT).
IEEE AITU 2024: Digital Generation Conference, March 2024
DOI: 10.1109/IEEECONF61558.2024.10585529IEEE AITU 2024: Digital Generation Conference, February 2024
DOI: 10.1109/IEEECONF61558.2024.10585385AITU Digital Generation 2023 Conference, March 2023
DOI: 10.13140/RG.2.2.35223.85927
Optimized Interpretable Kolmogorov-Arnold Networks
A deep learning framework for interpretable neural networks using advanced basis functions. The model provides symbolic representations andvisualizations that facilitate scientific understanding andregulatory compliance. As an open-source implementation,OIKAN represents a significant advancement in developingmachine learning models that balance predictive accuracy withinterpretability, meeting the growing demand for transparent AI systems in scientific and industrial applications.
